Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

• URL: http://arxiv.org/abs/2106.12384v1
• Date: Wed, 23 Jun 2021 13:24:39 GMT
• Title: Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations
• Authors: Qian Li, Hao Peng, Jianxin Li, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
• Abstract summary: This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process. Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods.
• Score: 70.35379323231241
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an argument's role often varies in different contexts. While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches. This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system. To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process. Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually. It then uses the newly obtained information to improve the decisions of previously extracted arguments. This two-way feedback process allows us to exploit the argument relations to effectively settle argument roles, leading to better sentence understanding and event extraction. Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods for the classification of events and argument role and argument identification.

Related papers

• Explicit, Implicit, and Scattered: Revisiting Event Extraction to Capture Complex Arguments [1.9820694575112385]
  Prior works formulate the extraction of event-specific arguments as a span extraction problem. We introduce two key argument types that cannot be modeled by existing EE frameworks. We develop a novel dataset, DiscourseEE, which includes 7,464 argument annotations from online health discourse.
  arXiv  Detail & Related papers  (2024-10-04T16:54:30Z)
• Global Constraints with Prompting for Zero-Shot Event Argument Classification [49.84347224233628]
  We propose to use global constraints with prompting to tackle event argument classification without any annotation and task-specific training. A pre-trained language model scores the new passages, making the initial prediction. Our novel prompt templates can easily adapt to all events and argument types without manual effort.
  arXiv  Detail & Related papers  (2023-02-09T06:39:29Z)
• Retrieval-Augmented Generative Question Answering for Event Argument Extraction [66.24622127143044]
  We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings.
  arXiv  Detail & Related papers  (2022-11-14T02:00:32Z)
• Open-Vocabulary Argument Role Prediction for Event Extraction [70.93524366880521]
  In this paper, we define this essential but under-explored task: open-vocabulary argument role prediction. The goal of this task is to infer a set of argument roles for a given event type. We propose a novel unsupervised framework, RolePred for this task.
  arXiv  Detail & Related papers  (2022-11-03T04:13:37Z)
• Dynamic Global Memory for Document-level Argument Extraction [63.314514124716936]
  We introduce a new global neural generation-based framework for document-level event argument extraction. We use a document memory store to record the contextual event information and leverage it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially.
  arXiv  Detail & Related papers  (2022-09-18T23:45:25Z)
• EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction [52.43978926985928]
  We introduce the Event-Aware Argument Extraction (EA$2$E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$2$E.
  arXiv  Detail & Related papers  (2022-05-30T04:33:51Z)
• Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder [7.60457018063735]
  We formalize event argument extraction (EAE) as a Seq2Seq-like learning problem for the first time. A neural architecture with a novel Bi-directional Entity-level Recurrent Decoder (BERD) is proposed to generate argument roles.
  arXiv  Detail & Related papers  (2021-07-01T02:55:12Z)
• Event Argument Extraction using Causal Knowledge Structures [9.56216681584111]
  Event Argument extraction refers to the task of extracting structured information from unstructured text for a particular event of interest. Most of the existing works model this task at a sentence level, restricting the context to a local scope. We propose an external knowledge aided approach to infuse document-level event information to aid the extraction of complex event arguments.
  arXiv  Detail & Related papers  (2021-05-02T13:59:07Z)
• Resource-Enhanced Neural Model for Event Argument Extraction [28.812507794694543]
  Event argument extraction aims to identify the arguments of an event and classify the roles that those arguments play. We propose a trigger-aware sequence encoder with several types of trigger-dependent sequence representations. Experiments on the English ACE2005 benchmark show that our approach achieves a new state-of-the-art.
  arXiv  Detail & Related papers  (2020-10-06T21:00:54Z)
• Event Extraction by Answering (Almost) Natural Questions [40.13163091122463]
  We introduce a new paradigm for event extraction by formulating it as a question answering (QA) task. Empirical results demonstrate that our framework outperforms prior methods substantially.
  arXiv  Detail & Related papers  (2020-04-28T16:15:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.